中文
相关论文

相关论文: HVM-1: Large-scale video models pretrained with ne…

200 篇论文

Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spanning over one hour and containing tens of thousands of…

计算机视觉与模式识别 · 计算机科学 2025-05-14 Heqing Zou , Tianze Luo , Guiyang Xie , Victor Xiao Jie Zhang , Fengmao Lv , Guangcong Wang , Junyang Chen , Zhuochen Wang , Hansheng Zhang , Huaijian Zhang

In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Ilan Naiman , Emanuel Ben-Baruch , Oron Anschel , Alon Shoshan , Igor Kviatkovsky , Manoj Aggarwal , Gerard Medioni

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive,…

计算机视觉与模式识别 · 计算机科学 2024-11-08 Keshigeyan Chandrasegaran , Agrim Gupta , Lea M. Hadzic , Taran Kota , Jimming He , Cristóbal Eyzaguirre , Zane Durante , Manling Li , Jiajun Wu , Li Fei-Fei

Human-centric generative models are becoming increasingly popular, giving rise to various innovative tools and applications, such as talking face videos conditioned on text or audio prompts. The core of these capabilities lies in powerful…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Donglin Di , He Feng , Wenzhang Sun , Yongjia Ma , Hao Li , Wei Chen , Lei Fan , Tonghua Su , Xun Yang

We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that…

计算机视觉与模式识别 · 计算机科学 2022-07-11 Hongwei Xue , Tiankai Hang , Yanhong Zeng , Yuchong Sun , Bei Liu , Huan Yang , Jianlong Fu , Baining Guo

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image…

Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video…

计算机视觉与模式识别 · 计算机科学 2023-08-25 David Fan , Jue Wang , Shuai Liao , Yi Zhu , Vimal Bhat , Hector Santos-Villalobos , Rohith MV , Xinyu Li

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos. However, their capacity to comprehend human-centric video data remains underexplored, primarily…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Yuxuan Cai , Jiangning Zhang , Zhenye Gan , Qingdong He , Xiaobin Hu , Junwei Zhu , Yabiao Wang , Chengjie Wang , Zhucun Xue , Chaoyou Fu , Xinwei He , Xiang Bai

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yongtao Ge , Kangyang Xie , Guangkai Xu , Mingyu Liu , Li Ke , Longtao Huang , Hui Xue , Hao Chen , Chunhua Shen

Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners…

计算机视觉与模式识别 · 计算机科学 2022-10-19 Zhan Tong , Yibing Song , Jue Wang , Limin Wang

Recent long-form video-language understanding benchmarks have driven progress in video large multimodal models (Video-LMMs). However, the scarcity of well-annotated long videos has left the training of hour-long Video-LMMs underexplored. To…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Jingyang Lin , Jialian Wu , Ximeng Sun , Ze Wang , Jiang Liu , Yusheng Su , Xiaodong Yu , Hao Chen , Jiebo Luo , Zicheng Liu , Emad Barsoum

In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which is long-time urged in this field. Our dataset, named DHF1K…

计算机视觉与模式识别 · 计算机科学 2018-05-29 Wenguan Wang , Jianbing Shen , Fang Guo , Ming-Ming Cheng , Ali Borji

Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding and address a fundamental issue pertaining to all…

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community. In this paper we propose a novel approach to this problem with Vector Quantized Variational…

计算机视觉与模式识别 · 计算机科学 2021-03-03 Jacob Walker , Ali Razavi , Aäron van den Oord

We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive…

计算机视觉与模式识别 · 计算机科学 2024-11-20 Mohammad Adiban , Kalin Stefanov , Sabato Marco Siniscalchi , Giampiero Salvi

In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lighting changes, and…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Xingyu Miao , Junting Dong , Qin Zhao , Yuhang Yang , Junhao Chen , Yang Long

Reconstructing human vision from brain activities has been an appealing task that helps to understand our cognitive process. Even though recent research has seen great success in reconstructing static images from non-invasive brain…

计算机视觉与模式识别 · 计算机科学 2023-05-22 Zijiao Chen , Jiaxin Qing , Juan Helen Zhou

Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst…

计算机视觉与模式识别 · 计算机科学 2022-10-11 Haosen Yang , Deng Huang , Bin Wen , Jiannan Wu , Hongxun Yao , Yi Jiang , Xiatian Zhu , Zehuan Yuan

Human detection in videos plays an important role in various real-life applications. Most traditional approaches depend on utilizing handcrafted features, which are problem-dependent and optimal for specific tasks. Moreover, they are highly…

机器学习 · 计算机科学 2026-01-06 Nouar AlDahoul , Aznul Qalid Md Sabri , Ali Mohammed Mansoor
‹ 上一页 1 2 3 10 下一页 ›